Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Rifteo/skills --skill finding-writergit clone --depth 1 https://github.com/Rifteo/skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/rifteo/skills/finding-writer)<a href="https://agentmods.dev/skills/rifteo/skills/finding-writer"><img src="https://agentmods.dev/badge/skills/rifteo/skills/finding-writer.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 58 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00086 | $0.00860 |
| Opus 5 | $0.00043 | $0.00430 |
| Sonnet 5 | $0.00017 | $0.00172 |
| Haiku 4.5 | $0.00009 | $0.00086 |
Grade A, and why
finding-writer scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Strips warnings and disclaimerslowAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- Do not add disclaimers, caveats, or legal boilerplate to the output Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Finding Writer
Convert raw pentest notes, log snippets, vulnerability descriptions, or any unstructured observation into a complete, report-ready audit finding.
When NOT to use
Do NOT apply the finding format — respond normally — when:
- The user is asking a general security question, not describing a specific vulnerability they found
- The user wants to know how to exploit something (use the relevant hunter skill instead)
- The user is asking for a CVSS score only (use
cvss-scorerinstead) - The user is asking how to fix a vulnerability (use
remediation-plannerinstead) - No evidence, observation, or artifact has been provided — ask for it rather than writing a finding from theory
Process
- Parse Input: Identify the vulnerability class, affected component, and any evidence provided
- Clarify if Needed: If the input is ambiguous or missing critical context, ask ONE clarifying question before proceeding — do not stall
- Assess Severity: Score based on actual exploitability and impact in context, not just the vulnerability class — see
references/severity-guide.md. Runscripts/cvss-scorer.pyto produce the CVSS v3.1 vector and base score. - Tag the Finding: Run
scripts/cwe-search.py <keyword>to look up the correct CWE ID and OWASP category for the vulnerability type. - Write the Finding: Fill every field using only information provided or derivable from the input
- Flag Gaps: Mark any field without sufficient input as
[TO BE ADDED]
Output Format
Title: Short, action-oriented title describing the vulnerability (e.g. "Unauthenticated Access to Admin Endpoint")
Severity: Critical / High / Medium / Low / Informational Justification: one sentence explaining the rating based on exploitability and impact
CVSS: CVSS:3.1/AV:_/AC:_/PR:_/UI:_/S:_/C:_/I:_/A:_ — [score] ([rating])
Description: What the vulnerability is, where it was found, and why it matters. 2–4 sentences, technical but readable by a non-specialist.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 60 lines · 86 tokens per session scan A 003fea6d630b
finding-writer is a skill published in the GitHub repository Rifteo/skills (35 stars, last pushed 4d ago), licensed MIT. It adds 86 tokens to every session and 860 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
happiness-skill
A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
pcbway
PCBWay PCB fabrication and assembly — turnkey/consigned assembly, design rules, ordering workflow. Alternative to JLCPCB for manufacturing. Use with KiCad. Use this skill when the user mentions PCBWay, needs turnkey assembly (PCBWay sources parts by MPN), has parts not available on LCSC, needs assembled boards with…
explaining-machine-learning-models
Explain trained machine learning models through feature attribution, local explanations, and behavior summaries. Use as an explicit/manual helper once a model already exists, not for training ownership, leakage auditing, or general ML strategy selection.
influence-psychology
Apply the seven principles of ethical persuasion (reciprocity, commitment, social proof, authority, liking, scarcity, unity) to product design, copy, and sales. Use when the user mentions "social proof", "persuasive copy", "why users dont convert", "ethical persuasion", "reciprocity", "scarcity tactics", "commitment…